{ "bcoid": "GLY_000647", "title": "Fruitfly Proteome Masterlist (UniProtKB)", "description": "The Fruitfly Proteome Masterlist dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions ...", "filename": "fruitfly_protein_masterlist.csv", "filetype": "csv", "categories": { "species": [ "Drosophila melanogaster" ], "molecule": [ "Protein" ], "tag": [ "Protein Canonical Accessions" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "M9PJ12-1...", "unreviewed..." ], [ "M9PJ12-1...", "unreviewed..." ] ], "headers": [ "uniprotkb_ca...", "status..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "status" }, { "type": "string", "label": "gene_name" }, { "type": "string", "label": "reviewed_isoforms" }, { "type": "string", "label": "unreviewed_isoforms" } ], [ "M9PJ12-1", "unreviewed", "CG32778", "", "M9PGE8-1" ], [ "M9PJ12-1", "unreviewed", "CG32778", "", "M9PGM4-1" ], [ "M9PJ12-1", "unreviewed", "CG32778", "", "M9PH00-1" ], [ "M9PJ12-1", "unreviewed", "CG32778", "", "M9PJ12-1" ], [ "M9PJ12-1", "unreviewed", "CG32778", "", "Q9W4N4-1" ], [ "M9PJ12-1", "unreviewed", "CG32778", "", "X2JCH4-1" ], [ "P40796-1", "reviewed", "La", "P40796-1", "" ], [ "P40797-1", "reviewed", "pnut", "P40797-1", "" ], [ "P40794-1", "reviewed", "bnk", "P40794-1", "" ], [ "P40795-1", "reviewed", "fog", "P40795-1", "A4V4V8-1" ], [ "P40792-1", "reviewed", "Rac1", "P40792-1", "M9PBH7-1" ], [ "P40793-1", "reviewed", "Cdc42", "P40793-1", "M9NFF8-1" ], [ "P40791-1", "reviewed", "Mef2", "P40791-1", "A0A0B4KEP4-1" ], [ "P40791-1", "reviewed", "Mef2", "P40791-2", "A0A0B4KFI1-1" ], [ "P40791-1", "reviewed", "Mef2", "P40791-3", "A0A6M3Q705-1" ], [ "P40791-1", "reviewed", "Mef2", "P40791-4", "A0A6M3Q797-1" ], [ "P40791-1", "reviewed", "Mef2", "P40791-6", "A0A6M3Q823-1" ], [ "P40791-1", "reviewed", "Mef2", "", "A0A6M3QA49-1" ], [ "P40798-1", "reviewed", "stc", "P40798-1", "M9PD57-1" ], [ "P40798-1", "reviewed", "stc", "P40798-2", "M9PDG3-1" ], [ "P40421-1", "reviewed", "rdgC", "P40421-1", "A0A4D6K426-1" ], [ "P40423-1", "reviewed", "sqh", "P40423-1", "F6J1D0-1" ], [ "P40427-1", "reviewed", "exd", "P40427-1", "M9PHV1-1" ], [ "A2VEV2-1", "unreviewed", "Dmel\\CG34323", "", "A2VEV2-1" ], [ "A2VEV0-1", "unreviewed", "Dmel\\CG34302", "", "A2VEV0-1" ], [ "P08841-1", "reviewed", "betaTub60D", "P08841-1", "A0A0B4LGH1-1" ], [ "Q9VE87-1", "reviewed", "hmw", "Q9VE87-1", "" ], [ "Q9VE86-1", "reviewed", "WRNexo", "Q9VE86-1", "E1JIP3-1" ], [ "Q9VE86-1", "reviewed", "WRNexo", "", "E8NH59-1" ], [ "Q9VE85-1", "unreviewed", "Nup43", "", "Q9VE85-1" ], [ "P05389-1", "reviewed", "RpLP2", "P05389-1", "" ], [ "A0A6H2EE55-1", "unreviewed", "Dmel\\CG14431", "", "A0A6H2EE55-1" ], [ "A0A6H2EE55-1", "unreviewed", "Dmel\\CG14431", "", "Q9W3U2-1" ], [ "A0A6F7UCJ3-1", "unreviewed", "GH14785", "", "A0A6F7UCJ3-1" ], [ "Q9VRR2-1", "reviewed", "PXo", "Q9VRR2-1", "A0A4D6K4X7-1" ], [ "Q9VRR3-1", "unreviewed", "CG10727", "", "Q9VRR3-1" ], [ "Q9VRR0-1", "unreviewed", "Dmel\\CG10486", "", "M9ND52-1" ], [ "Q9VRR0-1", "unreviewed", "Dmel\\CG10486", "", "Q9VRR0-1" ], [ "P04388-1", "reviewed", "Ras64B", "P04388-1", "" ], [ "A1ZB47-1", "unreviewed", "CG5719", "", "A1ZB47-1" ], [ "A1ZB42-1", "reviewed", "MED9", "A1ZB42-1", "" ], [ "A1ZB48-1", "unreviewed", "Dmel\\CG14500", "", "A1ZB48-1" ], [ "A1ZB49-1", "unreviewed", "Dmel\\CG30114", "", "A1ZB49-1" ], [ "Q9VLI9-1", "unreviewed", "Trs23", "", "Q9VLI9-1" ], [ "Q9VLI1-1", "unreviewed", "LManIV", "", "Q9VLI1-1" ], [ "Q9VLI0-1", "unreviewed", "LManV", "", "Q9VLI0-1" ], [ "Q9VLI3-1", "unreviewed", "Dmel\\CG12438", "", "Q9VLI3-1" ], [ "Q9VLI2-1", "unreviewed", "LManIII", "", "Q9VLI2-1" ], [ "Q9VLI4-1", "unreviewed", "raw", "", "X2J5A2-1" ], [ "Q9VLI4-1", "unreviewed", "raw", "", "Q9VLI4-1" ], [ "Q9VLI4-1", "unreviewed", "raw", "", "Q9VLI5-1" ], [ "Q9VLI6-1", "unreviewed", "CatB", "", "Q9VLI6-1" ], [ "Q02870-1", "reviewed", "hay", "Q02870-1", "B7Z0G1-1" ], [ "Q7JUM3-1", "unreviewed", "PIG-A", "", "Q7JUM3-1" ], [ "Q8SXV2-1", "unreviewed", "Dmel\\CG31675", "", "Q8SXV2-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9NER8-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PB30-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PB31-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PBZ4-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PC45-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PC48-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PCJ6-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PCJ8-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PEI1-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PEI7-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9NE82-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PBZ0-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PC41-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PEH5-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9NCR4-1" ], [ "M9PB30-1", "unreviewed", "dpy", "", "M9PB32-1" ], [ "Q8SXV4-1", "unreviewed", "BcDNA:RH68528", "", "Q8SXV4-1" ], [ "Q9VGW4-1", "unreviewed", "Dmel\\CG14692", "", "Q9VGW4-1" ], [ "Q8SXV9-1", "unreviewed", "Dmel\\CG12998", "", "Q8SXV9-1" ], [ "Q9VGW5-1", "unreviewed", "BcDNA:RE74890", "", "Q9VGW5-1" ], [ "Q9VME8-1", "unreviewed", "ppk14", "", "Q9VME8-1" ], [ "Q9VME9-1", "unreviewed", "ppk7", "", "Q9VME9-1" ], [ "Q9VME0-1", "unreviewed", "Dmel\\CG13982", "", "Q9VME0-1" ], [ "Q9VME1-1", "unreviewed", "CG33295", "", "Q9VME1-1" ], [ "Q9VME2-1", "unreviewed", "Nepl6", "", "Q9VME2-1" ], [ "Q9VME3-1", "unreviewed", "Nepl5", "", "Q9VME3-1" ], [ "Q9VVS1-1", "unreviewed", "Dic4", "", "Q9VVS1-1" ], [ "Q9VVS1-1", "unreviewed", "Dic4", "", "M9PFM0-1" ], [ "Q9VVS3-1", "unreviewed", "anon-WO0118547.731", "", "Q9VVS3-1" ] ] }, "readme": "Name\n - Fruitfly Proteome Masterlist (UniProtKB)\n\nVersion\n - v-2.4.1\n\nCreated on\n - 2022-08-30T16:22:11.325302\n\nModified on\n - 2022-09-26T09:08:12.709716\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Fruitfly Proteome Masterlist dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - canonical accessions\n - gene name\n - protein isoforms\n - complete proteome\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: uniprot-proteome-drosophila-melanogaster.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-drosophila-melanogaster.nt\n Output Subdomain\n Name: fruitfly_protein_masterlist.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_masterlist.csv\n Name: fruitfly_protein_masterlist.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_masterlist.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"13824\"\n Name: \"status\"\n Description: \"Status of the protein record in UniProtKB database that can be reviewed for UniProtKB/Swiss-Prot entry or unreviewed for UniProtKB/TrEMBL entry\"\n Unique Values: \"2\"\n Name: \"gene_name\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\"\n Unique Values: \"13435\"\n Name: \"reviewed_isoforms\"\n Description: \"\"Protein records from UniProtKB/SwissProt database that have been manually curated and annotated based on experimental results\"\n Unique Values: \"5202\"\n Name: \"unreviewed_isoforms\"\n Description: \"Protein records from UniProtKB/TrEMBL database that have been computationally annotated\"\n Unique Values: \"18214\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/fruitfly_protein_masterlist.csv" }